Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
I18N_LLM_MODELNoOptional model name for live translation, e.g. gpt-4o-mini.
I18N_LLM_API_KEYNoAPI key for the OpenAI-compatible endpoint. Set this to enable live translation; otherwise localize returns providerMode: "jobs" and does zero network calls.
I18N_LLM_BASE_URLNoOpenAI-compatible endpoint base URL for live translation. Set this to enable live translation; otherwise localize returns providerMode: "jobs" and does zero network calls.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_localesA

List supported locales and their formatting rules (quotes, separators, date format, RTL, formality).

pseudo_localizeA

Generate pseudolocalized text (accented + expanded + bracketed) to catch hard-coded strings, truncation and layout breakage before real translation. Deterministic; safe for CI.

i18n_lintA

Lint a translated string against a locale's rules: number/date separators, quote style, CJK fullwidth punctuation, RTL bidi marks, placeholder parity with source, and length budget. Deterministic.

glossary_applyB

Enforce glossary/term consistency across target strings. Flags untranslated source terms and brand-term variants. Deterministic.

localizeA

Translate source text into one or more locales and post-process (lint + glossary). With an OpenAI-compatible provider configured it returns real translations; otherwise it returns structured translation jobs (it never fabricates output).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 5 tools

Disambiguation4/5

Each tool has a distinct primary purpose, but localize overlaps slightly with i18n_lint and glossary_apply because it performs post-processing. The descriptions clarify when to use each, so confusion is limited.

Naming Consistency4/5

All names use snake_case, which is consistent, but the structural pattern varies: list_locales and pseudo_localize are verb-like, i18n_lint and glossary_apply are noun-first, and localize is a bare verb. This is mostly predictable with minor deviations.

Tool Count5/5

Five tools is well-scoped for a focused i18n localization toolkit. Each tool earns its place by covering a specific stage of the localization workflow.

Completeness4/5

The surface covers locale inspection, pseudolocalization, linting, glossary enforcement, and translation, which is strong lifecycle coverage. Minor gaps exist around configuring translation providers or extracting strings from source files, but agents can work around these.